Could be amazing, but it's hard to judge if it will really work with say a 27 B model or larger. We can already get pretty good speed with a 2B model.
There is a time-consuming part, though, that is performed manually by our (human) team: implement the logic of the model in C++ and assembly code in a super-optimized way, co-designed for each specific hardware card.
This can take months.
We hope to accelerate the process with AI agents, but we're not there yet.